Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Can we have the dataset #3

Open
f16hari opened this issue Feb 25, 2020 · 6 comments
Open

Can we have the dataset #3

f16hari opened this issue Feb 25, 2020 · 6 comments

Comments

@f16hari
Copy link

f16hari commented Feb 25, 2020

so can you find time to upload the downloaded dataset through dropbox or google drive

@RouaL312
Copy link

how can i run convertwav_2spect.sh on windows 10?

@SuperKogito
Copy link

@hamzag95 i think it would be nice to add some lines to the readme explaining what the code does? voice classification is a broad term, is it a speaker classification based on voice, gender classification etc. ? Also, including the dependencies would be nice, like the Sox dependency ;)

To @f16hari point, having the dataset would help a lot (if you can disclose it). I only found the demo data.

@RouaL312 The .sh files are just shell scripts designed to be run by the Unix shell. The easiest way is to run the .sh in Linux virtual environment or install a shell prompt in windows which is now possible but you have to correctly add your dependencies to the path like installing Sox (used by the shell script in question), other run alternatives can be found here. In my opinion, a nice task /workaround for this is to go through the shell script and rewrite it in python by using pysox for example :) and later you can use your python code using anaconda or jupyter.

Best of luck to you all :))

@hamzag95
Copy link
Owner

hamzag95 commented Jun 5, 2020

A teammate at the time had the data, but it is now gone. However I hope to re-scrape that this summer since there seems to be high demand for it.

Also this was a project I did when I was new to DS/ML, so there is room for improvement with both the code and documentation of it. I'll try to keep this repo updated and hopefully later this summer there is better documented version.

Also @SuperKogito, thanks for the suggestion about pysox, was not aware of that.

@hamzag95
Copy link
Owner

hamzag95 commented Jun 17, 2020

just an update, my workload between research and work is quite high, so it doesn't seem likely I will get a chance to rescrape the data.

@filedeliver
Copy link

filedeliver commented Oct 20, 2020

Can you please comment on this dimension mismatch? The png provided from the training folders are all size of 513X800X4

image

@imavijit
Copy link

@filedeliver I also noticed that. Have you got any workaround, how to work this out?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

6 participants